Compare / Claude Opus 4.6 vs Gemini 2.5 Pro
Claude Opus 4.6 vs Gemini 2.5 Pro
16 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Opus 4.6 | Gemini 2.5 Pro |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,495 | 1,431 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,223 | 1,142 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,494 | 1,462 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,501 | 1,437 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,501 | 1,443 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,547 | 1,458 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,513 | 1,438 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,505 | 1,446 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,500 | 1,445 |
| tau2-benchreported | Consistency (pass^4)% of tasks | 11.3% | 1.0% |
| tau2-benchreported | Task success (pass^1)% of tasks | 27.3% | 13.7% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 3.0% | 19.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.41 | 0.40 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 70.9 | 65.2 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 99.8% | 99.1% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 12.2% | 7.0% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.